GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Remek
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Remek
Model Tree
speakleash/Bielik-4.5B-v3.0-Instruct
Input Modalities
Output Modalities
Supported Functionality
Agreement is the share of decisions where the port picks the same option as the bf16 release model on the development set dev v2 (MLX rows: every 3rd dev v2 decision, 1,700 decisions). Bars for this tier: agreement 2-10 >= 0.9415, agreement at reference margin >= 0.2 >= 0.9863, accuracy within 1 point of bf16, ECE at most +0.01. All ports of this tier:
| package | agreement with bf16 (options 2-10) | agreement at margin >= 0.2 | accuracy diff | ECE diff | size | speed | gate |
|---|---|---|---|---|---|---|---|
| FP8 | 0.9478 | 0.9890 | -0.0008 | +0.0009 | 4.9 GB | 38.6 dec/s c16, c1 p50 29 ms (H100) | PASS |
| GGUF Q8_0 | 0.9839 | 0.9988 | +0.0002 | +0.0035 | 4.8 GB | not measured in this release | PASS |
| GGUF Q5_K_M | 0.9569 | 0.9920 | -0.0039 | +0.0040 | 3.2 GB | not measured in this release | PASS |
| MLX 8-bit | 0.9792 | 0.9989 | +0.0000 | -0.0009 | 4.9 GB | 278 ms c1 p50, 698 ms for 5 questions (Mac) | PASS |
The ports are decision-layer checks against bf16, not new benchmarks; the model's own results are on basal-2.0-4.5B.
The same install as the bf16 model (quick start); then:
bash
basal-serve --model Remek/basal-2.0-4.5B-FP8 --mode fp8 --template-prefix off --port 8000--template-prefix off is needed for this model: the prompt-template cache failed its check.
An NVIDIA ModelOpt FP8 checkpoint that the basal engine v2.0.0 loads natively; needs a GPU with FP8 (sm89+, Hopper or Blackwell). In FP8 the batch can change near-tie decisions; --deterministic runs every request alone with full FP8 accumulation.
Speed: 38.6 dec/s c16, c1 p50 29 ms (H100); one NVIDIA H100 80GB (cluster node), one option order.
Engine. FlashAttention 2; compact rows and template prefix off (FP8 keeps FlashAttention 2 unless --attn fa3, which is faster but was not gated and changes some decisions near ties). Engine v2.0.0 schedules long requests (over 2,048 tokens) behind short ones: in a mixed load at 32 clients short requests answer in 0.81 s instead of 1.38 s (p50), and long requests take about 7% longer (p50 1.96 s instead of 1.83 s); --scheduler off serves in arrival order. The same basal engine v2.0.0 also serves the experimental basal-omni-1.0 models (images and audio): README.
CALIBRATION.json in this folder is a copy of the FP8 fit (CALIBRATION.fp8.json). basal-serve --mode fp8 loads CALIBRATION.<engine>.json for its engine when the folder has it, else CALIBRATION.json. A calibration fitted on bf16 readouts does not carry over exactly to a quantised port (an outside test of
basal-1.5 on Ollama saw 2.3% real error at the 1% threshold with the bf16 file), so a port-specific fit, where it passed,
uses the bf16 model's method on that port's own readouts of the same calibration splits, one option order:
basal-serve --mode fp8: Ships CALIBRATION.fp8.json, fitted on FP8 readouts of this port (same method as the bf16 fit, one option order); dev v2 ECE 0.0184 with the bf16 fit -> 0.0215 with this fit (in-sample), 0.0241 held-out (leave-one-family-out).Where a port uses the bf16 calibration, treat its confidence thresholds as approximate and fit your own with
basal-calibrate when they matter.
See the model card basal-2.0-4.5B for Werdykt, JDI, LEK, PL-Holdout and PL-Real numbers against basal-1.5 and the evaluation notes. This port is not scored separately on those benchmarks.
"facts": "auto")."max_error": 0.01
on an act or tool question defers every decision; use 0.05, or certify thresholds on your own data with basal-calibrate.act and multi over many labels are experimental. Up to 255 options per question (Ollama: 20); the context is
32,768 tokens. The 2.0 models ship no evidence head.bibtex
@software{kinas2026basal20, title = {basal-2.0: typed-decision models and inference engine for Polish and English}, author = {Kinas, Remigiusz}, year = {2026}, version = {2.0.0}, url = {https://github.com/rkinas/basal}}Apache-2.0. Fine-tuned from speakleash/Bielik-4.5B-v3.0-Instruct (Apache-2.0). Bielik is a project of SpeakLeash and ACK Cyfronet AGH.
basal-serve --model Remek/basal-2.0-4.5B-FP8 --mode fp8 --template-prefix off --port 8000@software{kinas2026basal20, title = {basal-2.0: typed-decision models and inference engine for Polish and English}, author = {Kinas, Remigiusz}, year = {2026}, version = {2.0.0}, url = {https://github.com/rkinas/basal}}